Standing Mandates
- NEVER start coding because the request "looks clear". Code written without a spec leaves nothing to count
against: unrequested changes and missing behaviour both pass unnoticed (teams bench: with no spec,
scope_match
could not even be measured). Write the spec first, get it approved, then code.
- A fact the request does not give is marked
[확인 필요: <fact>], never guessed; a guessed rule ships as code.
- Code that needs behaviour the spec lacks stops until the spec is amended and re-approved. Never amend the spec
to match code already written: the spec then proves nothing, because it was bent to fit the code it should judge.
Goal: every AC-n traces to a US-n, a task and a piece of evidence, and every change outside the spec is listed.
Spec-Driven Development
One flow from request to proof: spec, design, tasks, code, then a check of each criterion against evidence.
Not for an implementation plan or ticket breakdown alone (write:plans); the test-first loop itself
(develop:test-driven-development); choosing topology or datastore (develop:architecture-designer); running the
work through the multi-agent graph (teams:develop). A one-line fix → say so and skip.
Process
- Specify. Read the code and docs first; ask one line at most. Write
spec.md: problem, US-n stories,
AC-n criteria in Given/When/Then (each cites its US-n), out of scope, [확인 필요] items. Before the gate,
sweep for criteria the request implies but never states — inputs that must count as the same (case, whitespace,
encoding), resource bounds (growth, retention), behaviour while a state holds — each becomes an AC or a
[확인 필요] (bench: a spec without the sweep let Bob/bob each get their own lockout counter). Gate: show
the spec and wait for approval. No design or code before it.
- Design.
design.md: interface contracts, data model, decisions in one line each. Every item names the
AC-n it serves; an item serving none is cut.
- Tasks.
tasks.md: one task per AC (or a tight group), each with its failing test first and its IDs. Order by
dependency.
- Implement. Take tasks in order. A needed change the spec lacks goes spec first (amend, re-approve), then code.
Anything already changed outside the spec is logged, not hidden.
- Verify. For each
AC-n, run the check and record the test name or output. An AC with no evidence is
unfinished. List every out-of-spec change. Then write the tally.
Templates: references/templates.md. Store under specs/<feature>/, or where the project already keeps specs.
Output Template
Per step, the file named above. The closing report is only what follows — design.md and tasks.md stay files,
never pasted:
| AC |
Story |
Task |
Evidence (test name / output) |
Status |
| AC-1 |
US-1 |
T1 |
rejects expired token — pass |
met |
| AC-2 |
US-1 |
T2 |
— |
unmet |
Out-of-spec changes: file — what changed — why — spec amended? (or "none"). Open: each [확인 필요: …] with who
can answer.
Tally: <n> stories · <m> AC, <k> met with evidence · <j> out-of-spec changes · <o> open facts.
What Claude Does / What You Do
| Claude |
You |
| Drafts spec, design and tasks from code and your words |
Approve or amend the spec before anything is built |
| Marks missing facts, never fills them |
Answer each [확인 필요] |
| Amends the spec before any out-of-spec code |
Approve amendments |
| Runs each AC check and reports evidence |
Decide whether an unmet AC blocks release |
Related Skills
develop:test-driven-development — the red-green loop each task runs
write:spec — turn an already-settled conversation into a spec with no interview
write:plans — plan or ticket breakdown when only that is needed
teams:develop — run the approved spec through the multi-agent graph
1---2name: spec-driven-development3description: >-4 Use when a feature should be specified before it is coded — stories, acceptance criteria, tasks, a5 per-criterion check. Triggers: "스펙 먼저", "명세부터 쓰고 구현", "수용 기준 먼저", "spec first",6 "spec-driven development".7license: MIT8metadata:9 source: https://skillmd.com/skills/newkayak12/spec-driven-development10 version: "1.1.0"11scenarios:12 - "write the spec and acceptance criteria first, then implement"13 - "let's do spec-driven development on this feature"14 - "check that every acceptance criterion is actually met"15 - "스펙부터 쓰고 구현하자"16 - "수용 기준 먼저 정하고 코드 짜줘"17 - "명세 항목별로 구현이 맞는지 검증해줘"18compatibility:19 recommended:20 - think-tool21 optional:22 - sequential-thinking23 remote_mcp_note: >-24 think-tool이 있으면 수용 기준의 누락과 모호함을 더 잘 잡습니다.25 Claude 설정 → MCP Servers에서 remote SSE 엔드포인트를 추가하세요.26---2728## Standing Mandates2930- NEVER start coding because the request "looks clear". Code written without a spec leaves nothing to count31 against: unrequested changes and missing behaviour both pass unnoticed (teams bench: with no spec, `scope_match`32 could not even be measured). Write the spec first, get it approved, then code.33- A fact the request does not give is marked `[확인 필요: <fact>]`, never guessed; a guessed rule ships as code.34- Code that needs behaviour the spec lacks stops until the spec is amended and re-approved. Never amend the spec35 to match code already written: the spec then proves nothing, because it was bent to fit the code it should judge.3637Goal: every AC-n traces to a US-n, a task and a piece of evidence, and every change outside the spec is listed.3839# Spec-Driven Development4041One flow from request to proof: spec, design, tasks, code, then a check of each criterion against evidence.4243**Not for** an implementation plan or ticket breakdown alone (`write:plans`); the test-first loop itself44(`develop:test-driven-development`); choosing topology or datastore (`develop:architecture-designer`); running the45work through the multi-agent graph (`teams:develop`). A one-line fix → say so and skip.4647## Process48491. **Specify.** Read the code and docs first; ask one line at most. Write `spec.md`: problem, `US-n` stories,50 `AC-n` criteria in Given/When/Then (each cites its `US-n`), out of scope, `[확인 필요]` items. Before the gate,51 sweep for criteria the request implies but never states — inputs that must count as the same (case, whitespace,52 encoding), resource bounds (growth, retention), behaviour while a state holds — each becomes an AC or a53 `[확인 필요]` (bench: a spec without the sweep let `Bob`/`bob` each get their own lockout counter). **Gate:** show54 the spec and wait for approval. No design or code before it.552. **Design.** `design.md`: interface contracts, data model, decisions in one line each. Every item names the56 `AC-n` it serves; an item serving none is cut.573. **Tasks.** `tasks.md`: one task per AC (or a tight group), each with its failing test first and its IDs. Order by58 dependency.594. **Implement.** Take tasks in order. A needed change the spec lacks goes spec first (amend, re-approve), then code.60 Anything already changed outside the spec is logged, not hidden.615. **Verify.** For each `AC-n`, run the check and record the test name or output. An AC with no evidence is62 unfinished. List every out-of-spec change. Then write the tally.6364Templates: `references/templates.md`. Store under `specs/<feature>/`, or where the project already keeps specs.6566## Output Template6768Per step, the file named above. The closing report is only what follows — design.md and tasks.md stay files,69never pasted:7071| AC | Story | Task | Evidence (test name / output) | Status |72|---|---|---|---|---|73| AC-1 | US-1 | T1 | `rejects expired token` — pass | met |74| AC-2 | US-1 | T2 | — | unmet |7576Out-of-spec changes: file — what changed — why — spec amended? (or "none"). Open: each `[확인 필요: …]` with who77can answer.7879Tally: `<n>` stories · `<m>` AC, `<k>` met with evidence · `<j>` out-of-spec changes · `<o>` open facts.8081## What Claude Does / What You Do8283| Claude | You |84|--------|-----|85| Drafts spec, design and tasks from code and your words | Approve or amend the spec before anything is built |86| Marks missing facts, never fills them | Answer each `[확인 필요]` |87| Amends the spec before any out-of-spec code | Approve amendments |88| Runs each AC check and reports evidence | Decide whether an unmet AC blocks release |8990## Related Skills9192- `develop:test-driven-development` — the red-green loop each task runs93- `write:spec` — turn an already-settled conversation into a spec with no interview94- `write:plans` — plan or ticket breakdown when only that is needed95- `teams:develop` — run the approved spec through the multi-agent graph